Exposure Modeling of Transmission Towers for Large-Scale Natural Hazard Risk Assessments Based on Deep-Learning Object Detection Models

Exposure modeling plays a crucial role in disaster risk assessments by providing geospatial information about assets at risk and their characteristics. Detailed exposure data enhances the spatial representation of a rapidly changing environment, enabling decision-makers to develop effective policies...

Full description

Saved in:
Bibliographic Details
Main Authors: Luigi Cesarini, Rui Figueiredo, Xavier Romão, Mario Martina
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Infrastructures
Subjects:
Online Access:https://www.mdpi.com/2412-3811/10/7/152
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849733538864168960
author Luigi Cesarini
Rui Figueiredo
Xavier Romão
Mario Martina
author_facet Luigi Cesarini
Rui Figueiredo
Xavier Romão
Mario Martina
author_sort Luigi Cesarini
collection DOAJ
description Exposure modeling plays a crucial role in disaster risk assessments by providing geospatial information about assets at risk and their characteristics. Detailed exposure data enhances the spatial representation of a rapidly changing environment, enabling decision-makers to develop effective policies for reducing disaster risk. This work proposes and demonstrates a methodology linking volunteered geographic information from OpenStreetMap (OSM), street-level imagery from Google Street View (GSV), and deep learning object detection models into the automated creation of exposure datasets for power grid transmission towers, assets particularly vulnerable to strong wind, and other perils. Specifically, the methodology is implemented through a start-to-end pipeline that starts from the locations of transmission towers derived from OSM data to obtain GSV images capturing the towers in a given region, based on which their relevant features for risk assessment purposes are determined using two families of object detection models, i.e., single-stage and two-stage detectors. Both models adopted herein, You Only Look Once version 5 (YOLOv5) and Detectron2, achieved high values of mean average precision (mAP) for the identification task (83.67% and 88.64%, respectively), while Detectron2 was found to outperform YOLOv5 for the classification task with a mAP of 64.89% against a 50.62% of the single-stage detector. When applied to a pilot study area in northern Portugal comprising approximately 5.800 towers, the two-stage detector also exhibited higher confidence in its detection on a larger part of the study area, highlighting the potential of the approach for large-scale exposure modeling of transmission towers.
format Article
id doaj-art-642cc5d5f831456091e8097f14e5e450
institution DOAJ
issn 2412-3811
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Infrastructures
spelling doaj-art-642cc5d5f831456091e8097f14e5e4502025-08-20T03:08:01ZengMDPI AGInfrastructures2412-38112025-06-0110715210.3390/infrastructures10070152Exposure Modeling of Transmission Towers for Large-Scale Natural Hazard Risk Assessments Based on Deep-Learning Object Detection ModelsLuigi Cesarini0Rui Figueiredo1Xavier Romão2Mario Martina3Department of Sciences, Technologies and Society, Scuola Universitaria Superiore IUSS Pavia, 27100 Pavia, ItalyCIIMAR—Interdisciplinary Centre of Marine and Environmental Research, University of Porto, 4450-208 Matosinhos, PortugalCONSTRUCT-LESE, Faculty of Engineering, University of Porto, 4200-465 Porto, PortugalDepartment of Sciences, Technologies and Society, Scuola Universitaria Superiore IUSS Pavia, 27100 Pavia, ItalyExposure modeling plays a crucial role in disaster risk assessments by providing geospatial information about assets at risk and their characteristics. Detailed exposure data enhances the spatial representation of a rapidly changing environment, enabling decision-makers to develop effective policies for reducing disaster risk. This work proposes and demonstrates a methodology linking volunteered geographic information from OpenStreetMap (OSM), street-level imagery from Google Street View (GSV), and deep learning object detection models into the automated creation of exposure datasets for power grid transmission towers, assets particularly vulnerable to strong wind, and other perils. Specifically, the methodology is implemented through a start-to-end pipeline that starts from the locations of transmission towers derived from OSM data to obtain GSV images capturing the towers in a given region, based on which their relevant features for risk assessment purposes are determined using two families of object detection models, i.e., single-stage and two-stage detectors. Both models adopted herein, You Only Look Once version 5 (YOLOv5) and Detectron2, achieved high values of mean average precision (mAP) for the identification task (83.67% and 88.64%, respectively), while Detectron2 was found to outperform YOLOv5 for the classification task with a mAP of 64.89% against a 50.62% of the single-stage detector. When applied to a pilot study area in northern Portugal comprising approximately 5.800 towers, the two-stage detector also exhibited higher confidence in its detection on a larger part of the study area, highlighting the potential of the approach for large-scale exposure modeling of transmission towers.https://www.mdpi.com/2412-3811/10/7/152exposure modelingobject detectiontransmission towersOpenStreetMapstreet-level imagery
spellingShingle Luigi Cesarini
Rui Figueiredo
Xavier Romão
Mario Martina
Exposure Modeling of Transmission Towers for Large-Scale Natural Hazard Risk Assessments Based on Deep-Learning Object Detection Models
Infrastructures
exposure modeling
object detection
transmission towers
OpenStreetMap
street-level imagery
title Exposure Modeling of Transmission Towers for Large-Scale Natural Hazard Risk Assessments Based on Deep-Learning Object Detection Models
title_full Exposure Modeling of Transmission Towers for Large-Scale Natural Hazard Risk Assessments Based on Deep-Learning Object Detection Models
title_fullStr Exposure Modeling of Transmission Towers for Large-Scale Natural Hazard Risk Assessments Based on Deep-Learning Object Detection Models
title_full_unstemmed Exposure Modeling of Transmission Towers for Large-Scale Natural Hazard Risk Assessments Based on Deep-Learning Object Detection Models
title_short Exposure Modeling of Transmission Towers for Large-Scale Natural Hazard Risk Assessments Based on Deep-Learning Object Detection Models
title_sort exposure modeling of transmission towers for large scale natural hazard risk assessments based on deep learning object detection models
topic exposure modeling
object detection
transmission towers
OpenStreetMap
street-level imagery
url https://www.mdpi.com/2412-3811/10/7/152
work_keys_str_mv AT luigicesarini exposuremodelingoftransmissiontowersforlargescalenaturalhazardriskassessmentsbasedondeeplearningobjectdetectionmodels
AT ruifigueiredo exposuremodelingoftransmissiontowersforlargescalenaturalhazardriskassessmentsbasedondeeplearningobjectdetectionmodels
AT xavierromao exposuremodelingoftransmissiontowersforlargescalenaturalhazardriskassessmentsbasedondeeplearningobjectdetectionmodels
AT mariomartina exposuremodelingoftransmissiontowersforlargescalenaturalhazardriskassessmentsbasedondeeplearningobjectdetectionmodels